AI Alignment Dialogues

An Interactive Approach to AI Alignment in Support Agents

Conference Paper (2022)
Author(s)

P.Y. Chen (TU Delft - Interactive Intelligence)

Research Group
Interactive Intelligence
Copyright
© 2022 P.Y. Chen
DOI related publication
https://doi.org/10.1145/3514094.3539531
More Info
expand_more
Publication Year
2022
Language
English
Copyright
© 2022 P.Y. Chen
Research Group
Interactive Intelligence
Pages (from-to)
894
ISBN (electronic)
978-1-4503-9247-1
Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Abstract

This project proposes a different way of looking at AI alignment, namely by introducing AI Alignment Dialogues. We argue that alignment dialogues have a number of advantages in comparison to data-driven approaches, especially for behaviour support agents, which aim to support users in achieving their desired future behaviours rather than their current behaviours. The advantages of alignment dialogues include allowing the users to directly convey higher-level concepts to the agent and making the agent more transparent and trusted.

Files

3514094.3539531.pdf
(pdf | 0.805 Mb)
License info not available